Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

ggml : group all experts in a single ggml_mul_mat_id #6505

Merged
merged 22 commits into from
Apr 18, 2024
Merged

ggml : group all experts in a single ggml_mul_mat_id #6505

merged 22 commits into from
Apr 18, 2024

Commits on Apr 5, 2024

  1. ggml : group all experts in a single ggml_mul_mat_id 

    cuda : improve mmid row copy
    @slaren
    slaren committed Apr 5, 2024
    Configuration menu
    Copy the full SHA
    ea2b795 View commit details
    Browse the repository at this point in the history

Commits on Apr 7, 2024

  1. minor

    @slaren
    slaren committed Apr 7, 2024
    Configuration menu
    Copy the full SHA
    1b5d78d View commit details
    Browse the repository at this point in the history

  2. fix windows build

    @slaren
    slaren committed Apr 7, 2024
    Configuration menu
    Copy the full SHA
    bc61554 View commit details
    Browse the repository at this point in the history

  3. refactor moe ffn to llm_build_moe_ffn

    @slaren
    slaren committed Apr 7, 2024
    Configuration menu
    Copy the full SHA
    f3f7627 View commit details
    Browse the repository at this point in the history

  4. cleanup

    @slaren
    slaren committed Apr 7, 2024
    Configuration menu
    Copy the full SHA
    23f7d71 View commit details
    Browse the repository at this point in the history

Commits on Apr 8, 2024

  1. update imatrix

    @slaren
    slaren committed Apr 8, 2024
    Configuration menu
    Copy the full SHA
    9a43e80 View commit details
    Browse the repository at this point in the history

Commits on Apr 12, 2024

  1. minor

    @slaren
    slaren committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    47c3867 View commit details
    Browse the repository at this point in the history

  2. Merge remote-tracking branch 'origin/master' into sl/moe-rework-2

    @slaren
    slaren committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    137fbb8 View commit details
    Browse the repository at this point in the history

Commits on Apr 17, 2024

  1. add metal impl

    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    fc363e4 View commit details
    Browse the repository at this point in the history

  2. Merge remote-tracking branch 'origin/master' into sl/moe-rework-2

    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    42003fd View commit details
    Browse the repository at this point in the history

  3. fix merge 

    ggml-ci
    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    fb168ac View commit details
    Browse the repository at this point in the history

  4. cleanup

    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    bf56fde View commit details
    Browse the repository at this point in the history

  5. cuda : fix bin bcast with non-cont src0

    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    d68c935 View commit details
    Browse the repository at this point in the history

  6. cleanup 

    ggml-ci
    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    997a9b5 View commit details
    Browse the repository at this point in the history

  7. cuda : fix binbcast

    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    f7fe79a View commit details
    Browse the repository at this point in the history

  8. Merge remote-tracking branch 'origin/master' into sl/moe-rework-2

    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    d18b19c View commit details
    Browse the repository at this point in the history

  9. cuda : fix warnings

    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    0e6963d View commit details
    Browse the repository at this point in the history

  10. metal : enable buffer log prints again

    @slaren
    slaren committed Apr 17, 2024
    Configuration menu
    Copy the full SHA
    4d8fe07 View commit details
    Browse the repository at this point in the history

Commits on Apr 18, 2024

  1. llama : simplify moe reshapes 

    ggml-ci
    @ggerganov
    ggerganov committed Apr 18, 2024
    Configuration menu
    Copy the full SHA
    2080a97 View commit details
    Browse the repository at this point in the history

  2. ggml-ci

    @slaren
    slaren committed Apr 18, 2024
    Configuration menu
    Copy the full SHA
    4980e35 View commit details
    Browse the repository at this point in the history

  3. test-backend-ops : only run all mul mat tests for base types 

    ggml-ci
    @slaren
    slaren committed Apr 18, 2024
    Configuration menu
    Copy the full SHA
    bd17f27 View commit details
    Browse the repository at this point in the history

  4. llama : disable moe offloading with SYCL

    @slaren
    slaren committed Apr 18, 2024
    Configuration menu
    Copy the full SHA
    ba5b546 View commit details
    Browse the repository at this point in the history